[PR]上記の広告は3ヶ月以上新規記事投稿のないブログに表示されています。新しい記事を書く事で広告が消えます。
"""Gated recurrent unit (GRU) with nunits cells."""
with vs.variable_scope(scope or type(self).__name__): # "GRUCell"
with vs.variable_scope("Gates"): # Reset gate and update gate.
# We start with bias of 1.0 to not reset and not update.
r, u = array_ops.split(1, 2, _linear([inputs, state],
2 * self._num_units, True, 1.0))
r, u = sigmoid(r), sigmoid(u)
with vs.variable_scope("Candidate"):
c = self._activation(_linear([inputs, r * state],
self._num_units, True))
new_h = u * state + (1 - u) * cdef _linear(args, output_size, bias, bias_start=0.0, scope=None):
"""Linear map: sum_i(args[i] * W[i]), where W[i] is a variable.
Args:
args: a 2D Tensor or a list of 2D, batch x n, Tensors.
output_size: int, second dimension of W[i].
bias: boolean, whether to add a bias term or not.
bias_start: starting value to initialize the bias; 0 by default.
scope: VariableScope for the created subgraph; defaults to "Linear".
Returns:
A 2D Tensor with shape [batch x output_size] equal to
sum_i(args[i] * W[i]), where W[i]s are newly created matrices.
Raises:
ValueError: if some of the arguments has unspecified or wrong shape.
"""
if args is None or (nest.is_sequence(args) and not args):
raise ValueError("`args` must be specified")
if not nest.is_sequence(args):
args = [args]
# Calculate the total size of arguments on dimension 1.
total_arg_size = 0
shapes = [a.get_shape().as_list() for a in args]
for shape in shapes:
if len(shape) != 2:
raise ValueError("Linear is expecting 2D arguments: %s" % str(shapes))
if not shape[1]:
raise ValueError("Linear expects shape[1] of arguments: %s" % str(shapes))
else:
total_arg_size += shape[1]
# Now the computation.
with vs.variable_scope(scope or "Linear"):
matrix = vs.get_variable("Matrix", [total_arg_size, output_size])# <<<
if len(args) == 1:
res = math_ops.matmul(args[0], matrix)
else:
res = math_ops.matmul(array_ops.concat(1, args), matrix)# <<<
if not bias:
return res
bias_term = vs.get_variable(
"Bias", [output_size],
initializer=init_ops.constant_initializer(bias_start))
return res + bias_term